Ioannis Athanasiadis, Marc Rußwurm, Thijs Van Der Plas, Jacob Bakermans, Vishal Nedungadi, Gabrielė Tij Ūnaitytė
We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| vdplasthijs/better_together | — | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| calculate_complementarity | Ran | vdplasthijs/better_together/src/overlap_utils.py code served (permissive licence) · get_code("9ad2f7346a32062b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Earth embedding models transform Earth observation data into embeddings uniquely tied to locations on the Earth's surface. These models are typically evaluated in isolation, comparing the downstream task performance across different Earth embeddings. However, spatially aligned embeddings can naturally be fused, providing richer information per location, a capability that isolated evaluations fail to capture. We therefore propose assessing Earth embeddings by their complementarity: the performance gain of fused embeddings over the best single-model baseline. To operationalise this, we introduce an embedding complementarity index applicable to any embedding and task, and evaluate four Earth embedding models (AlphaEarth, Tessera, GeoCLIP, SatCLIP) in isolation, in all pairs, and jointly across six downstream tasks. Fused embeddings outperform the best single model in four out of six tasks, confirming that single-embedding evaluations often underestimate Earth embedding capabilities. Complementarity proves both task-and location-dependent. Further, for a land cover regression task, we find that complementarity is partially determined by the spatial scale of land cover classes. Complementarity reframes Earth embeddings: the greatest future gains may come not from any single Earth embedding model, but from combinations that are better together.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2605.18667")
get_code_for_paper("2605.18667")
have("2605.18667")
Connect an agent — have() is free.